Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements

Various information-processing capabilities of self- organizing nets of threshold elements are studied. A self-organizing net, learning from patterns or pattern sequences given from outside as stimuli, “remembers” some of them as stable equilibrium states or state-transition sequences of the net. A condition where many patterns and pattern sequences are remembered in a net at the same time is shown. The stability degree of their remembrance and recalling under noise disturbances is investigated theoretically. For this purpose, the stability of state transition in an autonomous logical net of threshold elements is studied by the use of characteristics of threshold elements. It is also shown that a self-organizing net forms a representative pattern from a given set of stimulus patterns and fixes it as a stable state. The representative pattern can be recalled from any member of the set. This kind of self-organizing net may be regarded as a model for associative memory, sequential recalling, and concept formation.